VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments
This dataset addresses the challenge of object localization for assistive technology for people with visual impairments, but it is incremental as it focuses on data collection and benchmarking.
The authors introduced VizWiz-FewShot, a dataset of nearly 10,000 segmentations in over 4,500 images taken by people with visual impairments, featuring objects with holes, varied sizes, and text. Analysis showed that three modern few-shot localization algorithms performed poorly on this dataset, struggling with holes, size extremes, and text absence.
We introduce a few-shot localization dataset originating from photographers who authentically were trying to learn about the visual content in the images they took. It includes nearly 10,000 segmentations of 100 categories in over 4,500 images that were taken by people with visual impairments. Compared to existing few-shot object detection and instance segmentation datasets, our dataset is the first to locate holes in objects (e.g., found in 12.3\% of our segmentations), it shows objects that occupy a much larger range of sizes relative to the images, and text is over five times more common in our objects (e.g., found in 22.4\% of our segmentations). Analysis of three modern few-shot localization algorithms demonstrates that they generalize poorly to our new dataset. The algorithms commonly struggle to locate objects with holes, very small and very large objects, and objects lacking text. To encourage a larger community to work on these unsolved challenges, we publicly share our annotated few-shot dataset at https://vizwiz.org .